Résumé:
Today, diabetes is one of the most common chronic diseases that can cause certain complications that can sometimes cause death. So, there is an urgent need for a prognostic tool that can help doctors detect the disease at an early stage and recommend the neces- sary lifestyle changes to stop the progression of this disease. Deep learning is an urgent need today to eliminate human effort and offer higher automation with fewer errors. In this project, a diabetes detection and prediction system is developed based on a deep lear- ning approach (ANN+GAN). Experiments conducted on the Pima data collection have given encouraging prediction results in comparison with two other machine learning approaches that we have implemented, namely: SVM and KNN.